Model comparison
DeepSeek Coder 33B vs DeepSeek V4 Flash
DeepSeek V4 Flash has enough public results to be ranked (#35); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek Coder 33B scores higher in 0 categories and DeepSeek V4 Flash in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek V4 Flash leads 47.9 to 38.0.
Side by side
| DeepSeek Coder 33B | DeepSeek V4 Flash | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 38.9 | 53.6 |
| Released | 2023-11-02 | 2026-04-24 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 393K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 9 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek Coder 33B: 38.0 (#184), DeepSeek V4 Flash: 47.9 (#59)
| Benchmark | DeepSeek Coder 33B | DeepSeek V4 Flash |
|---|---|---|
| FrontierCode | — | 18.8% |
| LMArena WebDev | — | 1582 |
| SciCode | — | 49.9% |
| WeirdML | — | 63% |
| BigCodeBench Instruct | 42% | — |
| LMArena Coding | — | 1457 |
| BigCodeBench Complete | 51.1% | — |
| ALE-Bench | — | 1,306 |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |
Reasoning Not comparable
DeepSeek Coder 33B: —, DeepSeek V4 Flash: 53.7 (#30)
| Benchmark | DeepSeek Coder 33B | DeepSeek V4 Flash |
|---|---|---|
| Epoch Capabilities Index | 96.32 | 154.49 |
| ARC-AGI-2 | — | 61.4% |
| SimpleBench | — | 61.1% |
| Kagi LLM Benchmark | — | 52.2% |
| NYT Connections (extended) | — | 89.6% |
| ARC-AGI-1 | — | 89% |
| CritPt | — | 16.6% |
| Chess Puzzles | — | 33% |
| LMArena Hard Prompts | — | 1444 |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 90.9% |
| LMCA | — | 41.7% |
| WinoGrande | 62% | — |
Math Not comparable
DeepSeek Coder 33B: —, DeepSeek V4 Flash: 60.3 (#37)
| Benchmark | DeepSeek Coder 33B | DeepSeek V4 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 57.5% |
| FrontierMath Tier 4 | — | 24.4% |
| MathArena Final-Answer Competitions | — | 76.5% |
| OTIS Mock AIME 2024-2025 | — | 94.4% |
| ProofBench | — | 56% |
| LMArena Math | — | 1427 |
| GSM8K | 35.4% | — |
Knowledge Not comparable
DeepSeek Coder 33B: —, DeepSeek V4 Flash: 55.4 (#48)
| Benchmark | DeepSeek Coder 33B | DeepSeek V4 Flash |
|---|---|---|
| GPQA Diamond | — | 91% |
| SimpleQA Verified | — | 33.6% |
| LMArena Expert | — | 1441 |
| ARC (AI2) Challenge | 42.2% | — |
| MMLU | 39.4% | — |
Multilingual Not comparable
DeepSeek Coder 33B: —, DeepSeek V4 Flash: 53.0 (#72)
| Benchmark | DeepSeek Coder 33B | DeepSeek V4 Flash |
|---|---|---|
| LMArena Non-English | — | 1420 |
| LMArena Chinese | — | 1468 |
| LMArena French | — | 1439 |
| LMArena German | — | 1418 |
| LMArena Japanese | — | 1406 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1436 |
Instruction Following Not comparable
DeepSeek Coder 33B: —, DeepSeek V4 Flash: 74.9 (#81)
| Benchmark | DeepSeek Coder 33B | DeepSeek V4 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1421 |
Long Context Not comparable
DeepSeek Coder 33B: —, DeepSeek V4 Flash: 43.8 (#85)
| Benchmark | DeepSeek Coder 33B | DeepSeek V4 Flash |
|---|---|---|
| LMArena Longer Query | — | 1434 |
Writing & Preference Not comparable
DeepSeek Coder 33B: —, DeepSeek V4 Flash: 63.8 (#61)
| Benchmark | DeepSeek Coder 33B | DeepSeek V4 Flash |
|---|---|---|
| LMArena Text | — | 1432 |
| LMArena Creative Writing | — | 1403 |
| EQ-Bench Creative Writing | — | 1559 |
| LMArena Multi-Turn | — | 1449 |
Frequently asked questions
Is DeepSeek Coder 33B better than DeepSeek V4 Flash?
DeepSeek V4 Flash has enough public results to be ranked (#35); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or DeepSeek V4 Flash better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 38.0 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and DeepSeek V4 Flash share?
1 benchmark has published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and DeepSeek V4 Flash has 41.